Data Engineer
Data Scientist
Data Analyst
Data Engineer
Data Scientist
Data Analyst
Data Engineer and Data Scientist
With over 9 years of experience in game data analytics, I have a strong background in Python, SQL, Apache Spark, and Airflow. I’ve led analytics for a game with over 2 million monthly active users and helped increase FIFA Online 4’s revenue by 10% year-over-year. My expertise in data-driven insights and collaboration with cross-functional teams has improved user retention by 12% and led to the development of 20+ real-time data dashboards, enabling faster decision-making across teams.
9
Years of Experience
2M
Senior Data Analyst for a game with MAU of
20+
Dashboards with Real-Time Analytics
Professional Experience
Implementing data pipelines using Apache Kafka and Spark, optimizing real-time data flow. Managed large datasets efficiently and improved system response time by 20%, enabling faster decision-making. Proficient in Python, Airflow, and Docker for seamless data processing and automation.
Leveraging advanced analytics tools like Python and SQL to drive insights and decision-making. Increased user retention by 12% through in-depth user behavior analysis, and contributed to 10% revenue growth with targeted data-driven strategies. Expert in building real-time dashboards using Tableau.
Personal Projects
Developed a Document AI chatbot using Solar LLM and Kafka for efficient real-time retrieval and generation, with a focus on building a RAG (Retrieval-Augmented Generation) chatbot designed to handle complex documents and provide real-time, accurate answers.
A Dockerized PySpark and Elasticsearch Pipeline for Real-time Data Visualization: Utilized financial API data to create an end-to-end processing pipeline with Docker, PySpark, Elasticsearch, and Kibana for real-time financial data visualization.
Utilized U.S. COVID-19 data (2020–2023) to create a comprehensive real-time visualization pipeline using Docker, PySpark, Elasticsearch, and Kibana, focusing on healthcare insights and trends. The project highlighted key pandemic aspects, such as mortality rates and underlying health conditions, offering insights for public health decisions.
Python, Pandas, Seaborn, and Matplotlib used to preprocess and analyze large-scale MMORPG player data. Focused on identifying relationships between combat power progression and dungeon/quest engagement.
PyCaret and Gradient Boosting Regressor used to predict next month’s login days based on current attendance, spending, and combat power. Aimed to understand user engagement patterns by applying advanced regression techniques.
Utilized Python and libraries such as Pandas, PyCaret, Seaborn, and Matplotlib to conduct classification analysis on player combat power progression. Project aimed to predict future combat power levels and understand engagement with in-game activities like dungeon participation.
Utilized Python, Pandas, Matplotlib, and MiniBatch KMeans to perform clustering analysis on user data, identifying unique user segments based on metrics such as user level, quarterly attendance, quarterly payment, and combat power. Analysis supported retention event planning by focusing on user engagement levels.
Data Cleaning and Behavioral Analysis of Challenger and Professional Gamers: Leveraged the League of Legends API to clean and analyze gameplay data, focusing on the behaviors of top Challenger players and professional e-sports gamers. Conducted extensive data cleaning and visualized the findings using Python.
Developed a Python-based simulation to analyze a probability-based item in an MMORPG’s in-game store. The project aimed to evaluate different player strategies and assess their efficiency in earning points and rewards based on randomized draws.